Catastrophic forgetting is a major issue in task-incremental learning, where a neural network loses what it has learned in previous tasks after being trained on new tasks. A number of architecture-based approaches have been proposed to address ...

• Learning function is adaptively selected in the training process.
• Learning function selection is transformed a multi-armed bandit problem.
• A novel parallel learning function combining influence function is explored.
• Influence ...

Adaptive Kriging surrogate modeling has been widely used in reliability analysis, of which the core is the adaptive learning process. However, for the adaptive learning process, there are two limitations in previous studies: on the one hand, ...

The performance of intelligent fault diagnosis models is often hindered by the lack of available samples, a common issue in both the few-shot learning and imbalanced learning problems. While data generation has been shown to be an effective ...

• A self-reasoning training strategy is proposed.
• A generation model driven by multi-domain information is developed.
• The quality (similarity and diversity) of the generated samples is enhanced.

In this article, we focus on a design problem of flow distribution structure in nuclear reactor pressure vessel within the meshless topology optimization framework. A novel meshless particle method, NURBS-based particle hydrodynamics (NBPH) method,...

• A novel method is proposed for time-dependent hybrid reliability analysis;
• Time-dependent failure probability is cast as a high-dimensional Gaussian integral;
• The most probable point trajectory is surrogated by Kriging method;
• ...

Time-dependent reliability analysis is capable of evaluating the reliability of the system over its full life cycle, which is of highly concerned for designers. In practice, some uncertainties cannot be simply described by a deterministic ...

With the massive growth of edge devices, how to provide users with video recommendation services in a mobile edge environment has become a research hotspot. Most traditional video recommendation methods regard the relationship between user and ...

The natural distribution of industrial data is imbalanced, which deteriorates the performance of intelligent fault diagnostic models. Although cost-sensitive learning is an effective method for solving the data imbalance problem, it ...

• A novel cost-adaptive calculation method is proposed.
• The cost varies ...

In response to the problems of data missing, data exception and data duplication in electronic reconnaissance satellite intelligence processing, based on big data architecture and by comprehensive use of big data analysis techniques such as data cleaning ...

This paper presents a unique solution to the problem of planar compliant mechanism design by means of geometric morphing technology and isogeometric analysis (IGA). A new transformable triangular mesh (TTM) component is developed based on ...

Multi-person pose estimation has achieved great progress in recent years, even though, the precise prediction for occluded and invisible hard keypoints remains challenging. Most of the human pose estimation networks are equipped with an image ...

This article presents a way of optimizing the conduction topology for heat-generating structures by means of transformable triangular mesh (TTM) algorithm which is implemented in an explicit and geometrical way. Unlike the traditional optimization ...

Pneumatic soft robots show great potential application value in the field of hand rehabilitation. This paper presents a novel pneumatic soft robotic glove for hand rehabilitation with a portable pneumatic box. The glove uses positive-negative pneumatic ...

Within social networks user influence may be modelled based on user interactions. Further, it is typical to recommend users to others. What is the role of user influence in user recommendation? In this paper, we first propose to use a node embedding ...

This paper presents a non-iterative topology optimizer for conductive heat transfer structures with the help of deep learning. An artificial neural network is trained to deal with the black-and-white pixel images and generate near-...

• Non-iterative topology optimizer for conductive heat transfer structures with the help of deep learning.

Parametric parts can be instantiated into geometrically-different part instances, which presents a great challenge for the existing geometric-based sketch retrieval algorithms. Our main idea for this problem comes from the observation: ...

• A parametric part is approximated by topological view-dependent graphs (VD graphs).

There is no agreed definition of social capital in the literature. However, one interpretation is that it refers to those resources embedded in an individual's social network offering benefits to that individual in relation to achieving goals and ...

The imitation of the functions of soft animals has always been the goal of soft robotic design. However, most of the current soft terrestrial robots just imitate the basic gaits and are difficult to perform in three dimensional space. In this work, we ...

This work presents a novel variable stiffness structure consisting of a fiber-constrained dielectric elastomer tube filled with insulating oil. The tensile stiffness of the structure can be adjusted by voltages and its initial value can be customized ...

• It is proposed that the missing value in a record is handled by utilising the values of the corresponding fields in the k-NNs of this record.

The problem of record linkage is to identify records from two datasets, which refer to the same entities (e.g. patients). A particular issue of record linkage is the presence of missing values in records, which has not been fully ...

• A novel unsupervised approach to record linkage has been proposed.
• The approach ...

Record linkage is a process of identifying records that refer to the same real-world entity. Many existing approaches to record linkage apply supervised machine learning techniques to generate a classification model that classifies a ...